© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9458
    Prev
    Next
    INDEX
    Explanations

    -ed, -ish, -y, -ive endings

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on specialized technical or domain-specific jargon terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deewana
    0.87
     ადამიან
    0.86
     기준으로
    0.84
    ύ
    0.82
    īn
    0.82
     isomers
    0.81
     inequities
    0.80
    ‌లు
    0.80
    ‌కు
    0.79
     manures
    0.77
    POSITIVE LOGITS
    ing
    1.22
    ة
    1.09
    ות
    1.02
    িং
    1.00
    ន៍
    0.93
    ed
    0.93
    ات
    0.85
    ส์
    0.84
    oretically
    0.82
    able
    0.81
    Activations Density 2.781%

    No Known Activations